Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 337
• Descripción:
• Frecuencia: mes
• Variables: fecha_cnt, tmax, tmin
• Dimensiones del mapa: 5,5
• Iteraciones: 1000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-337.rds.xz")
summary(model)

SOM of size 5x5 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 0.156.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

   1    2    3    4    5    6    7    8    9   10   11   12   13   14   15   16 
3962 3789 5482 5689 1955 3188 3654 4025 3636 4547 4866 3832 3739 5121 4197 3131 
  17   18   19   20   21   22   23   24   25 
4437 4117 3892 3256 1899 3633 3785 4283  766 

Comprobación de nodos vacíos:

dim_model <- 5*5;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

      fecha_cnt       tmax       tmin
[1,] -0.1042546 -0.8954702 -0.8972276
[2,] -0.8533906 -0.1765840 -0.2110912

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

fecha_cnt      tmin      tmax 
0.9766933 0.9750699 0.9735719 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 3.000   Min.   :172.0   Min.   : 26.0   Min.   :  0.0   Min.   :0  
 1st Qu.: 6.000   1st Qu.:233.0   1st Qu.:126.0   1st Qu.:  1.0   1st Qu.:0  
 Median : 8.000   Median :262.0   Median :151.0   Median :  6.0   Median :0  
 Mean   : 7.587   Mean   :264.8   Mean   :152.3   Mean   : 10.9   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:293.0   3rd Qu.:179.0   3rd Qu.: 15.0   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :422.0   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.78   1st Qu.: -5.6983   1st Qu.:  33.0  
 Median : 0.00000   Median :40.41   Median : -3.4503   Median :  98.0  
 Mean   : 0.00355   Mean   :39.13   Mean   : -3.6413   Mean   : 315.7  
 3rd Qu.: 0.00000   3rd Qu.:41.70   3rd Qu.:  0.4731   3rd Qu.: 582.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 8.00   Min.   :-24.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:11.00   1st Qu.:115.0   1st Qu.:  28.00   1st Qu.:  6.00  
 Median :11.00   Median :147.0   Median :  58.00   Median : 16.00  
 Mean   :11.21   Mean   :141.7   Mean   :  54.87   Mean   : 23.75  
 3rd Qu.:12.00   3rd Qu.:174.0   3rd Qu.:  84.00   3rd Qu.: 33.00  
 Max.   :12.00   Max.   :223.0   Max.   : 143.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.: -5.4981  
 Median :0.0000000   Median :  0.0000   Median :41.15   Median : -2.9056  
 Mean   :0.0005093   Mean   :  0.3386   Mean   :40.53   Mean   : -2.8760  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.36   3rd Qu.:  0.4914  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  69.0  
 Median : 442.0  
 Mean   : 551.5  
 3rd Qu.: 779.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip      
 Min.   :1.000   Min.   :-53.0   Min.   :-121.00   Min.   :  0.00  
 1st Qu.:2.000   1st Qu.:125.0   1st Qu.:  27.00   1st Qu.:  5.00  
 Median :3.000   Median :157.0   Median :  58.00   Median : 13.00  
 Mean   :2.798   Mean   :151.7   Mean   :  56.43   Mean   : 18.92  
 3rd Qu.:4.000   3rd Qu.:184.0   3rd Qu.:  84.00   3rd Qu.: 26.00  
 Max.   :7.000   Max.   :258.0   Max.   : 185.00   Max.   :371.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :   0.000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:38.88   1st Qu.: -5.6417  
 Median :0.000000   Median :   0.000   Median :40.96   Median : -3.4503  
 Mean   :0.000544   Mean   :   1.092   Mean   :39.87   Mean   : -3.4682  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.33   3rd Qu.:  0.4914  
 Max.   :6.000000   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 316.0  
 Mean   : 475.6  
 3rd Qu.: 690.0  
 Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 3.000   Min.   :172.0   Min.   : 26.0   Min.   :  0.0   Min.   :0  
 1st Qu.: 6.000   1st Qu.:233.0   1st Qu.:126.0   1st Qu.:  1.0   1st Qu.:0  
 Median : 8.000   Median :262.0   Median :151.0   Median :  6.0   Median :0  
 Mean   : 7.587   Mean   :264.8   Mean   :152.3   Mean   : 10.9   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:293.0   3rd Qu.:179.0   3rd Qu.: 15.0   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :422.0   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.78   1st Qu.: -5.6983   1st Qu.:  33.0  
 Median : 0.00000   Median :40.41   Median : -3.4503   Median :  98.0  
 Mean   : 0.00355   Mean   :39.13   Mean   : -3.6413   Mean   : 315.7  
 3rd Qu.: 0.00000   3rd Qu.:41.70   3rd Qu.:  0.4731   3rd Qu.: 582.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 8.00   Min.   :-24.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:11.00   1st Qu.:115.0   1st Qu.:  28.00   1st Qu.:  6.00  
 Median :11.00   Median :147.0   Median :  58.00   Median : 16.00  
 Mean   :11.21   Mean   :141.7   Mean   :  54.87   Mean   : 23.75  
 3rd Qu.:12.00   3rd Qu.:174.0   3rd Qu.:  84.00   3rd Qu.: 33.00  
 Max.   :12.00   Max.   :223.0   Max.   : 143.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.: -5.4981  
 Median :0.0000000   Median :  0.0000   Median :41.15   Median : -2.9056  
 Mean   :0.0005093   Mean   :  0.3386   Mean   :40.53   Mean   : -2.8760  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.36   3rd Qu.:  0.4914  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  69.0  
 Median : 442.0  
 Mean   : 551.5  
 3rd Qu.: 779.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :1.000   Min.   : 87.0   Min.   : 14.00   Min.   :  0.00   Min.   :0  
 1st Qu.:2.000   1st Qu.:155.0   1st Qu.: 59.00   1st Qu.:  5.00   1st Qu.:0  
 Median :3.000   Median :175.0   Median : 76.00   Median : 14.00   Median :0  
 Mean   :3.155   Mean   :175.1   Mean   : 81.08   Mean   : 19.18   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:195.0   3rd Qu.: 96.00   3rd Qu.: 27.00   3rd Qu.:0  
 Max.   :7.000   Max.   :258.0   Max.   :185.00   Max.   :371.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.78   1st Qu.: -6.0442   1st Qu.:  27.0  
 Median : 0.00000   Median :40.66   Median : -3.6781   Median :  85.0  
 Mean   : 0.04773   Mean   :39.28   Mean   : -3.8560   Mean   : 289.2  
 3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.:  0.4914   3rd Qu.: 445.0  
 Max.   :41.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin              precip      
 Min.   :1.000   Min.   :-53.0   Min.   :-121.000   Min.   :  0.00  
 1st Qu.:1.000   1st Qu.: 88.0   1st Qu.:  -4.000   1st Qu.:  5.00  
 Median :2.000   Median :111.0   Median :  15.000   Median : 13.00  
 Mean   :2.124   Mean   :107.5   Mean   :   9.945   Mean   : 18.42  
 3rd Qu.:3.000   3rd Qu.:132.0   3rd Qu.:  29.000   3rd Qu.: 24.00  
 Max.   :7.000   Max.   :250.0   Max.   :  61.000   Max.   :309.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:40.66   1st Qu.: -4.5353  
 Median :0.000000   Median :   0.000   Median :41.60   Median : -2.7331  
 Mean   :0.001569   Mean   :   3.062   Mean   :40.99   Mean   : -2.7370  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.36   3rd Qu.:  0.4483  
 Max.   :6.000000   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.: 459.0  
 Median : 691.0  
 Mean   : 827.1  
 3rd Qu.: 990.0  
 Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin           precip            nevada 
 Min.   : 5.000   Min.   :217   Min.   :111.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:281   1st Qu.:167.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 8.000   Median :301   Median :184.0   Median :  2.000   Median :0  
 Mean   : 7.866   Mean   :301   Mean   :184.8   Mean   :  6.275   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:321   3rd Qu.:203.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403   Max.   :254.0   Max.   :320.000   Max.   :0  
   prof_nieve           longitud        latitud            altitud      
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:0.0000000   1st Qu.:37.19   1st Qu.: -5.6156   1st Qu.:  27.0  
 Median :0.0000000   Median :39.01   Median : -2.9056   Median :  81.0  
 Mean   :0.0001276   Mean   :38.28   Mean   : -3.4573   Mean   : 231.1  
 3rd Qu.:0.0000000   3rd Qu.:41.11   3rd Qu.:  0.4942   3rd Qu.: 459.0  
 Max.   :2.0000000   Max.   :43.57   Max.   :  4.2156   Max.   :1167.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 3.000   Min.   :172.0   Min.   : 26.0   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:223.0   1st Qu.:114.0   1st Qu.:  3.00   1st Qu.:0  
 Median : 7.000   Median :241.0   Median :133.0   Median :  9.00   Median :0  
 Mean   : 7.422   Mean   :243.5   Mean   :133.2   Mean   : 13.63   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:264.0   3rd Qu.:151.0   3rd Qu.: 19.00   3rd Qu.:0  
 Max.   :12.000   Max.   :336.0   Max.   :215.0   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.98   1st Qu.: -5.7333   1st Qu.:  35.0  
 Median : 0.00000   Median :40.95   Median : -3.6325   Median : 185.0  
 Mean   : 0.00557   Mean   :39.63   Mean   : -3.7498   Mean   : 365.6  
 3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.:  0.3264   3rd Qu.: 632.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 8.00   Min.   :-24.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:11.00   1st Qu.:115.0   1st Qu.:  28.00   1st Qu.:  6.00  
 Median :11.00   Median :147.0   Median :  58.00   Median : 16.00  
 Mean   :11.21   Mean   :141.7   Mean   :  54.87   Mean   : 23.75  
 3rd Qu.:12.00   3rd Qu.:174.0   3rd Qu.:  84.00   3rd Qu.: 33.00  
 Max.   :12.00   Max.   :223.0   Max.   : 143.00   Max.   :299.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.49   1st Qu.: -5.4981  
 Median :0.0000000   Median :  0.0000   Median :41.15   Median : -2.9056  
 Mean   :0.0005093   Mean   :  0.3386   Mean   :40.53   Mean   : -2.8760  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.36   3rd Qu.:  0.4914  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  69.0  
 Median : 442.0  
 Mean   : 551.5  
 3rd Qu.: 779.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :1.000   Min.   : 87.0   Min.   : 14.00   Min.   :  0.00   Min.   :0  
 1st Qu.:2.000   1st Qu.:155.0   1st Qu.: 59.00   1st Qu.:  5.00   1st Qu.:0  
 Median :3.000   Median :175.0   Median : 76.00   Median : 14.00   Median :0  
 Mean   :3.155   Mean   :175.1   Mean   : 81.08   Mean   : 19.18   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:195.0   3rd Qu.: 96.00   3rd Qu.: 27.00   3rd Qu.:0  
 Max.   :7.000   Max.   :258.0   Max.   :185.00   Max.   :371.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.78   1st Qu.: -6.0442   1st Qu.:  27.0  
 Median : 0.00000   Median :40.66   Median : -3.6781   Median :  85.0  
 Mean   : 0.04773   Mean   :39.28   Mean   : -3.8560   Mean   : 289.2  
 3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.:  0.4914   3rd Qu.: 445.0  
 Max.   :41.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin              precip      
 Min.   :1.000   Min.   :-53.0   Min.   :-121.000   Min.   :  0.00  
 1st Qu.:1.000   1st Qu.: 88.0   1st Qu.:  -4.000   1st Qu.:  5.00  
 Median :2.000   Median :111.0   Median :  15.000   Median : 13.00  
 Mean   :2.124   Mean   :107.5   Mean   :   9.945   Mean   : 18.42  
 3rd Qu.:3.000   3rd Qu.:132.0   3rd Qu.:  29.000   3rd Qu.: 24.00  
 Max.   :7.000   Max.   :250.0   Max.   :  61.000   Max.   :309.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:40.66   1st Qu.: -4.5353  
 Median :0.000000   Median :   0.000   Median :41.60   Median : -2.7331  
 Mean   :0.001569   Mean   :   3.062   Mean   :40.99   Mean   : -2.7370  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.36   3rd Qu.:  0.4483  
 Max.   :6.000000   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.: 459.0  
 Median : 691.0  
 Mean   : 827.1  
 3rd Qu.: 990.0  
 Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin           precip            nevada 
 Min.   : 5.000   Min.   :217   Min.   :111.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:281   1st Qu.:167.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 8.000   Median :301   Median :184.0   Median :  2.000   Median :0  
 Mean   : 7.866   Mean   :301   Mean   :184.8   Mean   :  6.275   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:321   3rd Qu.:203.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403   Max.   :254.0   Max.   :320.000   Max.   :0  
   prof_nieve           longitud        latitud            altitud      
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:0.0000000   1st Qu.:37.19   1st Qu.: -5.6156   1st Qu.:  27.0  
 Median :0.0000000   Median :39.01   Median : -2.9056   Median :  81.0  
 Mean   :0.0001276   Mean   :38.28   Mean   : -3.4573   Mean   : 231.1  
 3rd Qu.:0.0000000   3rd Qu.:41.11   3rd Qu.:  0.4942   3rd Qu.: 459.0  
 Max.   :2.0000000   Max.   :43.57   Max.   :  4.2156   Max.   :1167.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 3.000   Min.   :172.0   Min.   : 26.0   Min.   :  0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:223.0   1st Qu.:114.0   1st Qu.:  3.00   1st Qu.:0  
 Median : 7.000   Median :241.0   Median :133.0   Median :  9.00   Median :0  
 Mean   : 7.422   Mean   :243.5   Mean   :133.2   Mean   : 13.63   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:264.0   3rd Qu.:151.0   3rd Qu.: 19.00   3rd Qu.:0  
 Max.   :12.000   Max.   :336.0   Max.   :215.0   Max.   :422.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.98   1st Qu.: -5.7333   1st Qu.:  35.0  
 Median : 0.00000   Median :40.95   Median : -3.6325   Median : 185.0  
 Mean   : 0.00557   Mean   :39.63   Mean   : -3.7498   Mean   : 365.6  
 3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.:  0.3264   3rd Qu.: 632.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt       tmax            tmin            precip           nevada 
 Min.   : 8   Min.   : 95.0   Min.   :  2.00   Min.   :  0.00   Min.   :0  
 1st Qu.:10   1st Qu.:149.0   1st Qu.: 61.00   1st Qu.:  7.00   1st Qu.:0  
 Median :11   Median :167.0   Median : 77.00   Median : 19.00   Median :0  
 Mean   :11   Mean   :165.9   Mean   : 77.76   Mean   : 26.04   Mean   :0  
 3rd Qu.:12   3rd Qu.:183.0   3rd Qu.: 95.00   3rd Qu.: 36.00   3rd Qu.:0  
 Max.   :12   Max.   :223.0   Max.   :143.00   Max.   :299.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.92   Min.   :-17.7550   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.37   1st Qu.: -5.6417   1st Qu.:  35.0  
 Median : 0.00000   Median :40.96   Median : -2.9553   Median : 127.0  
 Mean   : 0.04368   Mean   :40.26   Mean   : -2.9701   Mean   : 363.4  
 3rd Qu.: 0.00000   3rd Qu.:42.38   3rd Qu.:  0.4914   3rd Qu.: 567.0  
 Max.   :59.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 8.00   Min.   :-24.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:11.00   1st Qu.: 86.0   1st Qu.:   1.00   1st Qu.:  5.00  
 Median :12.00   Median :105.0   Median :  19.00   Median : 13.00  
 Mean   :11.57   Mean   :100.2   Mean   :  15.56   Mean   : 19.82  
 3rd Qu.:12.00   3rd Qu.:119.0   3rd Qu.:  34.00   3rd Qu.: 27.00  
 Max.   :12.00   Max.   :176.0   Max.   :  68.00   Max.   :252.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :  0.0000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:40.66   1st Qu.: -4.1269  
 Median :0.000000   Median :  0.0000   Median :41.60   Median : -2.6544  
 Mean   :0.001384   Mean   :  0.8453   Mean   :40.99   Mean   : -2.7142  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:42.36   3rd Qu.:  0.4914  
 Max.   :3.000000   Max.   :382.0000   Max.   :43.57   Max.   :  3.1817  
    altitud      
 Min.   :   2.0  
 1st Qu.: 513.0  
 Median : 704.0  
 Mean   : 874.7  
 3rd Qu.:1004.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :1.000   Min.   : 87.0   Min.   : 14.00   Min.   :  0.00   Min.   :0  
 1st Qu.:2.000   1st Qu.:155.0   1st Qu.: 59.00   1st Qu.:  5.00   1st Qu.:0  
 Median :3.000   Median :175.0   Median : 76.00   Median : 14.00   Median :0  
 Mean   :3.155   Mean   :175.1   Mean   : 81.08   Mean   : 19.18   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:195.0   3rd Qu.: 96.00   3rd Qu.: 27.00   3rd Qu.:0  
 Max.   :7.000   Max.   :258.0   Max.   :185.00   Max.   :371.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.78   1st Qu.: -6.0442   1st Qu.:  27.0  
 Median : 0.00000   Median :40.66   Median : -3.6781   Median :  85.0  
 Mean   : 0.04773   Mean   :39.28   Mean   : -3.8560   Mean   : 289.2  
 3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.:  0.4914   3rd Qu.: 445.0  
 Max.   :41.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin              precip      
 Min.   :1.000   Min.   :-53.0   Min.   :-121.000   Min.   :  0.00  
 1st Qu.:1.000   1st Qu.: 88.0   1st Qu.:  -4.000   1st Qu.:  5.00  
 Median :2.000   Median :111.0   Median :  15.000   Median : 13.00  
 Mean   :2.124   Mean   :107.5   Mean   :   9.945   Mean   : 18.42  
 3rd Qu.:3.000   3rd Qu.:132.0   3rd Qu.:  29.000   3rd Qu.: 24.00  
 Max.   :7.000   Max.   :250.0   Max.   :  61.000   Max.   :309.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :   0.000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:   0.000   1st Qu.:40.66   1st Qu.: -4.5353  
 Median :0.000000   Median :   0.000   Median :41.60   Median : -2.7331  
 Mean   :0.001569   Mean   :   3.062   Mean   :40.99   Mean   : -2.7370  
 3rd Qu.:0.000000   3rd Qu.:   0.000   3rd Qu.:42.36   3rd Qu.:  0.4483  
 Max.   :6.000000   Max.   :1834.000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.: 459.0  
 Median : 691.0  
 Mean   : 827.1  
 3rd Qu.: 990.0  
 Max.   :2535.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin           precip            nevada 
 Min.   : 5.000   Min.   :217   Min.   :111.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:281   1st Qu.:167.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 8.000   Median :301   Median :184.0   Median :  2.000   Median :0  
 Mean   : 7.866   Mean   :301   Mean   :184.8   Mean   :  6.275   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:321   3rd Qu.:203.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403   Max.   :254.0   Max.   :320.000   Max.   :0  
   prof_nieve           longitud        latitud            altitud      
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:0.0000000   1st Qu.:37.19   1st Qu.: -5.6156   1st Qu.:  27.0  
 Median :0.0000000   Median :39.01   Median : -2.9056   Median :  81.0  
 Mean   :0.0001276   Mean   :38.28   Mean   : -3.4573   Mean   : 231.1  
 3rd Qu.:0.0000000   3rd Qu.:41.11   3rd Qu.:  0.4942   3rd Qu.: 459.0  
 Max.   :2.0000000   Max.   :43.57   Max.   :  4.2156   Max.   :1167.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax          tmin           precip           nevada 
 Min.   : 8.000   Min.   :172   Min.   : 26.0   Min.   :  0.00   Min.   :0  
 1st Qu.: 9.000   1st Qu.:218   1st Qu.:111.0   1st Qu.:  4.00   1st Qu.:0  
 Median : 9.000   Median :236   Median :129.0   Median : 11.00   Median :0  
 Mean   : 9.486   Mean   :239   Mean   :127.2   Mean   : 16.78   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:259   3rd Qu.:145.0   3rd Qu.: 23.00   3rd Qu.:0  
 Max.   :12.000   Max.   :321   Max.   :192.0   Max.   :206.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.88   1st Qu.: -5.6492   1st Qu.:  44.0  
 Median : 0.00000   Median :40.96   Median : -3.6325   Median : 263.0  
 Mean   : 0.01153   Mean   :39.86   Mean   : -3.6453   Mean   : 402.2  
 3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.:  0.3181   3rd Qu.: 667.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt       tmax            tmin            precip           nevada 
 Min.   : 8   Min.   : 95.0   Min.   :  2.00   Min.   :  0.00   Min.   :0  
 1st Qu.:10   1st Qu.:149.0   1st Qu.: 61.00   1st Qu.:  7.00   1st Qu.:0  
 Median :11   Median :167.0   Median : 77.00   Median : 19.00   Median :0  
 Mean   :11   Mean   :165.9   Mean   : 77.76   Mean   : 26.04   Mean   :0  
 3rd Qu.:12   3rd Qu.:183.0   3rd Qu.: 95.00   3rd Qu.: 36.00   3rd Qu.:0  
 Max.   :12   Max.   :223.0   Max.   :143.00   Max.   :299.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.92   Min.   :-17.7550   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.37   1st Qu.: -5.6417   1st Qu.:  35.0  
 Median : 0.00000   Median :40.96   Median : -2.9553   Median : 127.0  
 Mean   : 0.04368   Mean   :40.26   Mean   : -2.9701   Mean   : 363.4  
 3rd Qu.: 0.00000   3rd Qu.:42.38   3rd Qu.:  0.4914   3rd Qu.: 567.0  
 Max.   :59.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 8.00   Min.   :-24.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:11.00   1st Qu.: 86.0   1st Qu.:   1.00   1st Qu.:  5.00  
 Median :12.00   Median :105.0   Median :  19.00   Median : 13.00  
 Mean   :11.57   Mean   :100.2   Mean   :  15.56   Mean   : 19.82  
 3rd Qu.:12.00   3rd Qu.:119.0   3rd Qu.:  34.00   3rd Qu.: 27.00  
 Max.   :12.00   Max.   :176.0   Max.   :  68.00   Max.   :252.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :  0.0000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:40.66   1st Qu.: -4.1269  
 Median :0.000000   Median :  0.0000   Median :41.60   Median : -2.6544  
 Mean   :0.001384   Mean   :  0.8453   Mean   :40.99   Mean   : -2.7142  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:42.36   3rd Qu.:  0.4914  
 Max.   :3.000000   Max.   :382.0000   Max.   :43.57   Max.   :  3.1817  
    altitud      
 Min.   :   2.0  
 1st Qu.: 513.0  
 Median : 704.0  
 Mean   : 874.7  
 3rd Qu.:1004.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :3.000   Min.   :178.0   Min.   : 57.0   Min.   :  0.00   Min.   :0  
 1st Qu.:5.000   1st Qu.:227.0   1st Qu.:116.0   1st Qu.:  2.00   1st Qu.:0  
 Median :6.000   Median :245.0   Median :136.0   Median :  8.00   Median :0  
 Mean   :5.861   Mean   :246.8   Mean   :137.7   Mean   : 11.25   Mean   :0  
 3rd Qu.:6.000   3rd Qu.:266.0   3rd Qu.:158.0   3rd Qu.: 16.00   3rd Qu.:0  
 Max.   :8.000   Max.   :336.0   Max.   :215.0   Max.   :422.00   Max.   :0  
   prof_nieve           longitud        latitud            altitud    
 Min.   : 0.000000   Min.   :27.82   Min.   :-17.8889   Min.   :   1  
 1st Qu.: 0.000000   1st Qu.:37.84   1st Qu.: -5.8728   1st Qu.:  33  
 Median : 0.000000   Median :40.82   Median : -3.6325   Median : 108  
 Mean   : 0.001057   Mean   :39.45   Mean   : -3.8289   Mean   : 338  
 3rd Qu.: 0.000000   3rd Qu.:42.23   3rd Qu.:  0.3664   3rd Qu.: 609  
 Max.   :11.000000   Max.   :43.57   Max.   :  4.2156   Max.   :2371  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :1.000   Min.   : 87.0   Min.   : 14.00   Min.   :  0.00   Min.   :0  
 1st Qu.:2.000   1st Qu.:155.0   1st Qu.: 59.00   1st Qu.:  5.00   1st Qu.:0  
 Median :3.000   Median :175.0   Median : 76.00   Median : 14.00   Median :0  
 Mean   :3.155   Mean   :175.1   Mean   : 81.08   Mean   : 19.18   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:195.0   3rd Qu.: 96.00   3rd Qu.: 27.00   3rd Qu.:0  
 Max.   :7.000   Max.   :258.0   Max.   :185.00   Max.   :371.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.78   1st Qu.: -6.0442   1st Qu.:  27.0  
 Median : 0.00000   Median :40.66   Median : -3.6781   Median :  85.0  
 Mean   : 0.04773   Mean   :39.28   Mean   : -3.8560   Mean   : 289.2  
 3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.:  0.4914   3rd Qu.: 445.0  
 Max.   :41.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin           precip      
 Min.   :1.000   Min.   : 36.0   Min.   :-80.0   Min.   :  0.00  
 1st Qu.:1.000   1st Qu.: 93.0   1st Qu.:  0.0   1st Qu.:  5.00  
 Median :2.000   Median :113.0   Median : 17.0   Median : 12.00  
 Mean   :2.112   Mean   :113.6   Mean   : 13.9   Mean   : 17.21  
 3rd Qu.:3.000   3rd Qu.:133.0   3rd Qu.: 30.0   3rd Qu.: 23.00  
 Max.   :7.000   Max.   :250.0   Max.   : 61.0   Max.   :309.00  
     nevada           prof_nieve         longitud        latitud       
 Min.   :0.000000   Min.   :  0.000   Min.   :28.31   Min.   :-16.499  
 1st Qu.:0.000000   1st Qu.:  0.000   1st Qu.:40.63   1st Qu.: -4.680  
 Median :0.000000   Median :  0.000   Median :41.52   Median : -2.906  
 Mean   :0.001675   Mean   :  0.966   Mean   :40.92   Mean   : -2.894  
 3rd Qu.:0.000000   3rd Qu.:  0.000   3rd Qu.:42.27   3rd Qu.: -1.008  
 Max.   :6.000000   Max.   :666.000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.: 445.0  
 Median : 674.0  
 Mean   : 743.9  
 3rd Qu.: 916.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax             tmin             precip      
 Min.   :1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.:1.000   1st Qu.:  3.00   1st Qu.: -61.75   1st Qu.: 16.25  
 Median :2.000   Median : 21.00   Median : -45.00   Median : 31.50  
 Mean   :2.305   Mean   : 18.14   Mean   : -48.66   Mean   : 36.34  
 3rd Qu.:3.000   3rd Qu.: 36.00   3rd Qu.: -33.00   3rd Qu.: 51.00  
 Max.   :6.000   Max.   : 84.00   Max.   :  -4.00   Max.   :180.00  
     nevada    prof_nieve        longitud        latitud            altitud    
 Min.   :0   Min.   :   0.0   Min.   :28.31   Min.   :-16.4992   Min.   :   4  
 1st Qu.:0   1st Qu.:   0.0   1st Qu.:41.00   1st Qu.: -3.6325   1st Qu.:1894  
 Median :0   Median :   0.0   Median :42.47   Median :  0.8842   Median :2230  
 Mean   :0   Mean   :  34.1   Mean   :41.93   Mean   : -0.4168   Mean   :2059  
 3rd Qu.:0   3rd Qu.:   0.0   3rd Qu.:42.64   3rd Qu.:  1.3656   3rd Qu.:2400  
 Max.   :0   Max.   :1834.0   Max.   :43.36   Max.   :  2.4378   Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax          tmin           precip            nevada 
 Min.   : 5.000   Min.   :217   Min.   :111.0   Min.   :  0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:281   1st Qu.:167.0   1st Qu.:  0.000   1st Qu.:0  
 Median : 8.000   Median :301   Median :184.0   Median :  2.000   Median :0  
 Mean   : 7.866   Mean   :301   Mean   :184.8   Mean   :  6.275   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:321   3rd Qu.:203.0   3rd Qu.:  8.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403   Max.   :254.0   Max.   :320.000   Max.   :0  
   prof_nieve           longitud        latitud            altitud      
 Min.   :0.0000000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:0.0000000   1st Qu.:37.19   1st Qu.: -5.6156   1st Qu.:  27.0  
 Median :0.0000000   Median :39.01   Median : -2.9056   Median :  81.0  
 Mean   :0.0001276   Mean   :38.28   Mean   : -3.4573   Mean   : 231.1  
 3rd Qu.:0.0000000   3rd Qu.:41.11   3rd Qu.:  0.4942   3rd Qu.: 459.0  
 Max.   :2.0000000   Max.   :43.57   Max.   :  4.2156   Max.   :1167.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax          tmin           precip           nevada 
 Min.   : 8.000   Min.   :172   Min.   : 26.0   Min.   :  0.00   Min.   :0  
 1st Qu.: 9.000   1st Qu.:218   1st Qu.:111.0   1st Qu.:  4.00   1st Qu.:0  
 Median : 9.000   Median :236   Median :129.0   Median : 11.00   Median :0  
 Mean   : 9.486   Mean   :239   Mean   :127.2   Mean   : 16.78   Mean   :0  
 3rd Qu.:10.000   3rd Qu.:259   3rd Qu.:145.0   3rd Qu.: 23.00   3rd Qu.:0  
 Max.   :12.000   Max.   :321   Max.   :192.0   Max.   :206.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.88   1st Qu.: -5.6492   1st Qu.:  44.0  
 Median : 0.00000   Median :40.96   Median : -3.6325   Median : 263.0  
 Mean   : 0.01153   Mean   :39.86   Mean   : -3.6453   Mean   : 402.2  
 3rd Qu.: 0.00000   3rd Qu.:42.24   3rd Qu.:  0.3181   3rd Qu.: 667.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt       tmax            tmin            precip           nevada 
 Min.   : 8   Min.   : 95.0   Min.   :  2.00   Min.   :  0.00   Min.   :0  
 1st Qu.:10   1st Qu.:149.0   1st Qu.: 61.00   1st Qu.:  7.00   1st Qu.:0  
 Median :11   Median :167.0   Median : 77.00   Median : 19.00   Median :0  
 Mean   :11   Mean   :165.9   Mean   : 77.76   Mean   : 26.04   Mean   :0  
 3rd Qu.:12   3rd Qu.:183.0   3rd Qu.: 95.00   3rd Qu.: 36.00   3rd Qu.:0  
 Max.   :12   Max.   :223.0   Max.   :143.00   Max.   :299.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.92   Min.   :-17.7550   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:38.37   1st Qu.: -5.6417   1st Qu.:  35.0  
 Median : 0.00000   Median :40.96   Median : -2.9553   Median : 127.0  
 Mean   : 0.04368   Mean   :40.26   Mean   : -2.9701   Mean   : 363.4  
 3rd Qu.: 0.00000   3rd Qu.:42.38   3rd Qu.:  0.4914   3rd Qu.: 567.0  
 Max.   :59.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin             precip      
 Min.   : 8.00   Min.   :-24.0   Min.   :-110.00   Min.   :  0.00  
 1st Qu.:11.00   1st Qu.: 86.0   1st Qu.:   1.00   1st Qu.:  5.00  
 Median :12.00   Median :105.0   Median :  19.00   Median : 13.00  
 Mean   :11.57   Mean   :100.2   Mean   :  15.56   Mean   : 19.82  
 3rd Qu.:12.00   3rd Qu.:119.0   3rd Qu.:  34.00   3rd Qu.: 27.00  
 Max.   :12.00   Max.   :176.0   Max.   :  68.00   Max.   :252.00  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :  0.0000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:40.66   1st Qu.: -4.1269  
 Median :0.000000   Median :  0.0000   Median :41.60   Median : -2.6544  
 Mean   :0.001384   Mean   :  0.8453   Mean   :40.99   Mean   : -2.7142  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:42.36   3rd Qu.:  0.4914  
 Max.   :3.000000   Max.   :382.0000   Max.   :43.57   Max.   :  3.1817  
    altitud      
 Min.   :   2.0  
 1st Qu.: 513.0  
 Median : 704.0  
 Mean   : 874.7  
 3rd Qu.:1004.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   :3.000   Min.   :178.0   Min.   : 57.0   Min.   :  0.00   Min.   :0  
 1st Qu.:5.000   1st Qu.:227.0   1st Qu.:116.0   1st Qu.:  2.00   1st Qu.:0  
 Median :6.000   Median :245.0   Median :136.0   Median :  8.00   Median :0  
 Mean   :5.861   Mean   :246.8   Mean   :137.7   Mean   : 11.25   Mean   :0  
 3rd Qu.:6.000   3rd Qu.:266.0   3rd Qu.:158.0   3rd Qu.: 16.00   3rd Qu.:0  
 Max.   :8.000   Max.   :336.0   Max.   :215.0   Max.   :422.00   Max.   :0  
   prof_nieve           longitud        latitud            altitud    
 Min.   : 0.000000   Min.   :27.82   Min.   :-17.8889   Min.   :   1  
 1st Qu.: 0.000000   1st Qu.:37.84   1st Qu.: -5.8728   1st Qu.:  33  
 Median : 0.000000   Median :40.82   Median : -3.6325   Median : 108  
 Mean   : 0.001057   Mean   :39.45   Mean   : -3.8289   Mean   : 338  
 3rd Qu.: 0.000000   3rd Qu.:42.23   3rd Qu.:  0.3664   3rd Qu.: 609  
 Max.   :11.000000   Max.   :43.57   Max.   :  4.2156   Max.   :2371  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin         precip           nevada 
 Min.   :1.000   Min.   : 99.0   Min.   : 14   Min.   :  0.00   Min.   :0  
 1st Qu.:2.000   1st Qu.:145.0   1st Qu.: 52   1st Qu.:  6.00   1st Qu.:0  
 Median :2.000   Median :159.0   Median : 65   Median : 16.00   Median :0  
 Mean   :2.546   Mean   :158.2   Mean   : 67   Mean   : 21.73   Mean   :0  
 3rd Qu.:3.000   3rd Qu.:172.0   3rd Qu.: 80   3rd Qu.: 30.00   3rd Qu.:0  
 Max.   :7.000   Max.   :219.0   Max.   :137   Max.   :371.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :28.31   Min.   :-17.7550   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.98   1st Qu.: -5.6492   1st Qu.:  27.0  
 Median : 0.00000   Median :40.82   Median : -2.9553   Median :  87.0  
 Mean   : 0.05262   Mean   :40.11   Mean   : -2.9391   Mean   : 281.6  
 3rd Qu.: 0.00000   3rd Qu.:42.43   3rd Qu.:  0.4942   3rd Qu.: 415.0  
 Max.   :41.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin           precip      
 Min.   :1.000   Min.   : 36.0   Min.   :-80.0   Min.   :  0.00  
 1st Qu.:1.000   1st Qu.: 93.0   1st Qu.:  0.0   1st Qu.:  5.00  
 Median :2.000   Median :113.0   Median : 17.0   Median : 12.00  
 Mean   :2.112   Mean   :113.6   Mean   : 13.9   Mean   : 17.21  
 3rd Qu.:3.000   3rd Qu.:133.0   3rd Qu.: 30.0   3rd Qu.: 23.00  
 Max.   :7.000   Max.   :250.0   Max.   : 61.0   Max.   :309.00  
     nevada           prof_nieve         longitud        latitud       
 Min.   :0.000000   Min.   :  0.000   Min.   :28.31   Min.   :-16.499  
 1st Qu.:0.000000   1st Qu.:  0.000   1st Qu.:40.63   1st Qu.: -4.680  
 Median :0.000000   Median :  0.000   Median :41.52   Median : -2.906  
 Mean   :0.001675   Mean   :  0.966   Mean   :40.92   Mean   : -2.894  
 3rd Qu.:0.000000   3rd Qu.:  0.000   3rd Qu.:42.27   3rd Qu.: -1.008  
 Max.   :6.000000   Max.   :666.000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.: 445.0  
 Median : 674.0  
 Mean   : 743.9  
 3rd Qu.: 916.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   :1.000   Min.   : 87.0   Min.   : 20.00   Min.   :  0.00   Min.   :0  
 1st Qu.:4.000   1st Qu.:185.0   1st Qu.: 74.00   1st Qu.:  6.00   1st Qu.:0  
 Median :4.000   Median :195.0   Median : 87.00   Median : 14.00   Median :0  
 Mean   :4.311   Mean   :194.5   Mean   : 88.29   Mean   : 17.74   Mean   :0  
 3rd Qu.:5.000   3rd Qu.:205.0   3rd Qu.:103.00   3rd Qu.: 25.00   3rd Qu.:0  
 Max.   :7.000   Max.   :258.0   Max.   :157.00   Max.   :279.00   Max.   :0  
   prof_nieve         longitud        latitud            altitud      
 Min.   : 0.0000   Min.   :28.31   Min.   :-17.7550   Min.   :   1.0  
 1st Qu.: 0.0000   1st Qu.:38.37   1st Qu.: -5.6417   1st Qu.:  43.3  
 Median : 0.0000   Median :40.96   Median : -2.9056   Median : 147.0  
 Mean   : 0.0511   Mean   :40.16   Mean   : -3.0224   Mean   : 364.3  
 3rd Qu.: 0.0000   3rd Qu.:42.33   3rd Qu.:  0.4914   3rd Qu.: 609.0  
 Max.   :38.0000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt          tmax            tmin           precip            nevada 
 Min.   :1.000   Min.   :158.0   Min.   :110.0   Min.   :  0.000   Min.   :0  
 1st Qu.:2.000   1st Qu.:203.0   1st Qu.:140.0   1st Qu.:  0.000   1st Qu.:0  
 Median :3.000   Median :212.0   Median :150.0   Median :  3.000   Median :0  
 Mean   :2.668   Mean   :213.1   Mean   :149.5   Mean   :  7.338   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:222.0   3rd Qu.:159.0   3rd Qu.: 10.000   3rd Qu.:0  
 Max.   :4.000   Max.   :256.0   Max.   :185.0   Max.   :145.000   Max.   :0  
   prof_nieve    longitud        latitud           altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.889   Min.   :  1.00  
 1st Qu.:0    1st Qu.:28.05   1st Qu.:-16.561   1st Qu.: 24.00  
 Median :0    Median :28.46   Median :-15.389   Median : 32.00  
 Mean   :0    Mean   :29.90   Mean   :-13.626   Mean   : 35.96  
 3rd Qu.:0    3rd Qu.:28.95   3rd Qu.:-13.600   3rd Qu.: 35.00  
 Max.   :0    Max.   :41.98   Max.   :  2.825   Max.   :632.00  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt          tmax             tmin             precip      
 Min.   :1.000   Min.   :-53.00   Min.   :-121.00   Min.   :  0.00  
 1st Qu.:1.000   1st Qu.:  3.00   1st Qu.: -61.75   1st Qu.: 16.25  
 Median :2.000   Median : 21.00   Median : -45.00   Median : 31.50  
 Mean   :2.305   Mean   : 18.14   Mean   : -48.66   Mean   : 36.34  
 3rd Qu.:3.000   3rd Qu.: 36.00   3rd Qu.: -33.00   3rd Qu.: 51.00  
 Max.   :6.000   Max.   : 84.00   Max.   :  -4.00   Max.   :180.00  
     nevada    prof_nieve        longitud        latitud            altitud    
 Min.   :0   Min.   :   0.0   Min.   :28.31   Min.   :-16.4992   Min.   :   4  
 1st Qu.:0   1st Qu.:   0.0   1st Qu.:41.00   1st Qu.: -3.6325   1st Qu.:1894  
 Median :0   Median :   0.0   Median :42.47   Median :  0.8842   Median :2230  
 Mean   :0   Mean   :  34.1   Mean   :41.93   Mean   : -0.4168   Mean   :2059  
 3rd Qu.:0   3rd Qu.:   0.0   3rd Qu.:42.64   3rd Qu.:  1.3656   3rd Qu.:2400  
 Max.   :0   Max.   :1834.0   Max.   :43.36   Max.   :  2.4378   Max.   :2535  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)